This is an R Markdown Notebook. When you execute code within the notebook, the results appear beneath the code.
Try executing this chunk by clicking the Run button within the chunk or by placing your cursor inside it and pressing Ctrl+Shift+Enter.
plot(cars)
Add a new chunk by clicking the Insert Chunk button on the toolbar or by pressing Ctrl+Alt+I.
When you save the notebook, an HTML file containing the code and output will be saved alongside it (click the Preview button or press Ctrl+Shift+K to preview the HTML file).
The preview shows you a rendered HTML copy of the contents of the editor. Consequently, unlike Knit, Preview does not run any R code chunks. Instead, the output of the chunk when it was last run in the editor is displayed.
library("tidyverse")
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ ggplot2 3.3.6 ✔ purrr 0.3.4
## ✔ tibble 3.1.8 ✔ dplyr 1.0.9
## ✔ tidyr 1.2.0 ✔ stringr 1.4.0
## ✔ readr 2.1.2 ✔ forcats 0.5.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
library("here")
## here() starts at C:/Users/Pongpisut_PC2019/Documents/Rstudio
library("skimr")
library("janitor")
##
## Attaching package: 'janitor'
##
## The following objects are masked from 'package:stats':
##
## chisq.test, fisher.test
library("dplyr")
library("lubridate")
##
## Attaching package: 'lubridate'
##
## The following objects are masked from 'package:base':
##
## date, intersect, setdiff, union
Setup Working Directory
getwd()
## [1] "C:/Users/Pongpisut_PC2019/Documents/Rstudio"
setwd("C:/Users/Pongpisut_PC2019/Documents")
getwd()
## [1] "C:/Users/Pongpisut_PC2019/Documents"
Loading all file
#2017
p10 <- read_csv("P1/201701_to_03.csv")
## Warning in gzfile(file, mode): cannot open compressed file 'C:/Users/PONGPI~2/
## AppData/Local/Temp/RtmpyoY9J6\file2af021b04ca8', probable reason 'No such file
## or directory'
## Rows: 431691 Columns: 12
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (6): start_time, end_time, from_station_name, to_station_name, usertype,...
## dbl (6): trip_id, bikeid, tripduration, from_station_id, to_station_id, birt...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p11 <- read_csv("P1/201704_to_06.csv")
## Rows: 1119814 Columns: 12
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (6): start_time, end_time, from_station_name, to_station_name, usertype,...
## dbl (6): trip_id, bikeid, tripduration, from_station_id, to_station_id, birt...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p12 <- read_csv("P1/201707_to_09.csv")
## Rows: 1608270 Columns: 12
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (6): start_time, end_time, from_station_name, to_station_name, usertype,...
## dbl (6): trip_id, bikeid, tripduration, from_station_id, to_station_id, birt...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p13 <- read_csv("P1/201710_to_12.csv")
## Rows: 669239 Columns: 12
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (6): start_time, end_time, from_station_name, to_station_name, usertype,...
## dbl (6): trip_id, bikeid, tripduration, from_station_id, to_station_id, birt...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
#2018
p14 <- read_csv("P1/201801_to_03.csv")
## Rows: 387145 Columns: 12
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (4): 03 - Rental Start Station Name, 02 - Rental End Station Name, User...
## dbl (5): 01 - Rental Details Rental ID, 01 - Rental Details Bike ID, 03 - R...
## dttm (2): 01 - Rental Details Local Start Time, 01 - Rental Details Local En...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p15 <- read_csv("P1/201804_to_06.csv")
## Rows: 1059681 Columns: 12
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (4): from_station_name, to_station_name, usertype, gender
## dbl (5): trip_id, bikeid, from_station_id, to_station_id, birthyear
## dttm (2): start_time, end_time
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p16 <- read_csv("P1/201807_to_09.csv")
## Rows: 1513570 Columns: 12
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (4): from_station_name, to_station_name, usertype, gender
## dbl (5): trip_id, bikeid, from_station_id, to_station_id, birthyear
## dttm (2): start_time, end_time
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p17 <- read_csv("P1/201810_to_12.csv")
## Rows: 642686 Columns: 12
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (4): from_station_name, to_station_name, usertype, gender
## dbl (5): trip_id, bikeid, from_station_id, to_station_id, birthyear
## dttm (2): start_time, end_time
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
#2019
p18 <- read_csv("P1/201901_to_03.csv")
## Rows: 365069 Columns: 12
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (4): from_station_name, to_station_name, usertype, gender
## dbl (5): trip_id, bikeid, from_station_id, to_station_id, birthyear
## dttm (2): start_time, end_time
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p19 <- read_csv("P1/201904_to_06.csv")
## Rows: 1108163 Columns: 12
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (4): 03 - Rental Start Station Name, 02 - Rental End Station Name, User...
## dbl (5): 01 - Rental Details Rental ID, 01 - Rental Details Bike ID, 03 - R...
## dttm (2): 01 - Rental Details Local Start Time, 01 - Rental Details Local En...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p20 <- read_csv("P1/201907_to_09.csv")
## Rows: 1640718 Columns: 12
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (4): from_station_name, to_station_name, usertype, gender
## dbl (5): trip_id, bikeid, from_station_id, to_station_id, birthyear
## dttm (2): start_time, end_time
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p21 <- read_csv("P1/201910_to_12.csv")
## Rows: 704054 Columns: 12
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (4): from_station_name, to_station_name, usertype, gender
## dbl (5): trip_id, bikeid, from_station_id, to_station_id, birthyear
## dttm (2): start_time, end_time
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
#2020
p22 <- read_csv("P1/202001_to_03.csv")
## Rows: 426887 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (5): ride_id, rideable_type, start_station_name, end_station_name, memb...
## dbl (6): start_station_id, end_station_id, start_lat, start_lng, end_lat, e...
## dttm (2): started_at, ended_at
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p23 <- read_csv("P1/202004.csv")
## Rows: 84776 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (5): ride_id, rideable_type, start_station_name, end_station_name, memb...
## dbl (6): start_station_id, end_station_id, start_lat, start_lng, end_lat, e...
## dttm (2): started_at, ended_at
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p24 <- read_csv("P1/202005.csv")
## Rows: 200274 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (5): ride_id, rideable_type, start_station_name, end_station_name, memb...
## dbl (6): start_station_id, end_station_id, start_lat, start_lng, end_lat, e...
## dttm (2): started_at, ended_at
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p25 <- read_csv("P1/202006.csv")
## Rows: 343005 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (5): ride_id, rideable_type, start_station_name, end_station_name, memb...
## dbl (6): start_station_id, end_station_id, start_lat, start_lng, end_lat, e...
## dttm (2): started_at, ended_at
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p26 <- read_csv("P1/202007.csv")
## Rows: 551480 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (5): ride_id, rideable_type, start_station_name, end_station_name, memb...
## dbl (6): start_station_id, end_station_id, start_lat, start_lng, end_lat, e...
## dttm (2): started_at, ended_at
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p27 <- read_csv("P1/202008.csv")
## Rows: 622361 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (5): ride_id, rideable_type, start_station_name, end_station_name, memb...
## dbl (6): start_station_id, end_station_id, start_lat, start_lng, end_lat, e...
## dttm (2): started_at, ended_at
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p28 <- read_csv("P1/202009.csv")
## Rows: 532958 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (5): ride_id, rideable_type, start_station_name, end_station_name, memb...
## dbl (6): start_station_id, end_station_id, start_lat, start_lng, end_lat, e...
## dttm (2): started_at, ended_at
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p29 <- read_csv("P1/202010.csv")
## Rows: 388653 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (5): ride_id, rideable_type, start_station_name, end_station_name, memb...
## dbl (6): start_station_id, end_station_id, start_lat, start_lng, end_lat, e...
## dttm (2): started_at, ended_at
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p30 <- read_csv("P1/202011.csv")
## Rows: 259716 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (5): ride_id, rideable_type, start_station_name, end_station_name, memb...
## dbl (6): start_station_id, end_station_id, start_lat, start_lng, end_lat, e...
## dttm (2): started_at, ended_at
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p31 <- read_csv("P1/202012.csv")
## Rows: 131573 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (7): ride_id, rideable_type, start_station_name, start_station_id, end_...
## dbl (4): start_lat, start_lng, end_lat, end_lng
## dttm (2): started_at, ended_at
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
#2021
p32 <- read_csv("P1/202101.csv")
## Rows: 96834 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (7): ride_id, rideable_type, start_station_name, start_station_id, end_...
## dbl (4): start_lat, start_lng, end_lat, end_lng
## dttm (2): started_at, ended_at
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p33 <- read_csv("P1/202102.csv")
## Rows: 49622 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (7): ride_id, rideable_type, start_station_name, start_station_id, end_...
## dbl (4): start_lat, start_lng, end_lat, end_lng
## dttm (2): started_at, ended_at
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p34 <- read_csv("P1/202103.csv")
## Rows: 228496 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (7): ride_id, rideable_type, start_station_name, start_station_id, end_...
## dbl (4): start_lat, start_lng, end_lat, end_lng
## dttm (2): started_at, ended_at
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p35 <- read_csv("P1/202104.csv")
## Rows: 337230 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (7): ride_id, rideable_type, start_station_name, start_station_id, end_...
## dbl (4): start_lat, start_lng, end_lat, end_lng
## dttm (2): started_at, ended_at
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p36 <- read_csv("P1/202105.csv")
## Rows: 531633 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (7): ride_id, rideable_type, start_station_name, start_station_id, end_...
## dbl (4): start_lat, start_lng, end_lat, end_lng
## dttm (2): started_at, ended_at
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p37 <- read_csv("P1/202106.csv")
## Rows: 729595 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (7): ride_id, rideable_type, start_station_name, start_station_id, end_...
## dbl (4): start_lat, start_lng, end_lat, end_lng
## dttm (2): started_at, ended_at
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p38 <- read_csv("P1/202107.csv")
## Rows: 822410 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (7): ride_id, rideable_type, start_station_name, start_station_id, end_...
## dbl (4): start_lat, start_lng, end_lat, end_lng
## dttm (2): started_at, ended_at
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p39 <- read_csv("P1/202108.csv")
## Rows: 804352 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (7): ride_id, rideable_type, start_station_name, start_station_id, end_...
## dbl (4): start_lat, start_lng, end_lat, end_lng
## dttm (2): started_at, ended_at
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p40 <- read_csv("P1/202109.csv")
## Rows: 756147 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (7): ride_id, rideable_type, start_station_name, start_station_id, end_...
## dbl (4): start_lat, start_lng, end_lat, end_lng
## dttm (2): started_at, ended_at
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p41 <- read_csv("P1/202110.csv")
## Rows: 631226 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (7): ride_id, rideable_type, start_station_name, start_station_id, end_...
## dbl (4): start_lat, start_lng, end_lat, end_lng
## dttm (2): started_at, ended_at
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p42 <- read_csv("P1/202111.csv")
## Rows: 359978 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (7): ride_id, rideable_type, start_station_name, start_station_id, end_...
## dbl (4): start_lat, start_lng, end_lat, end_lng
## dttm (2): started_at, ended_at
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p43 <- read_csv("P1/202112.csv")
## Rows: 247540 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (7): ride_id, rideable_type, start_station_name, start_station_id, end_...
## dbl (4): start_lat, start_lng, end_lat, end_lng
## dttm (2): started_at, ended_at
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
#2022
p44 <- read_csv("P1/202201.csv")
## Rows: 103770 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (7): ride_id, rideable_type, start_station_name, start_station_id, end_...
## dbl (4): start_lat, start_lng, end_lat, end_lng
## dttm (2): started_at, ended_at
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p45 <- read_csv("P1/202202.csv")
## Rows: 115609 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (7): ride_id, rideable_type, start_station_name, start_station_id, end_...
## dbl (4): start_lat, start_lng, end_lat, end_lng
## dttm (2): started_at, ended_at
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p46 <- read_csv("P1/202203.csv")
## Rows: 284042 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (7): ride_id, rideable_type, start_station_name, start_station_id, end_...
## dbl (4): start_lat, start_lng, end_lat, end_lng
## dttm (2): started_at, ended_at
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p47 <- read_csv("P1/202204.csv")
## Rows: 371249 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (7): ride_id, rideable_type, start_station_name, start_station_id, end_...
## dbl (4): start_lat, start_lng, end_lat, end_lng
## dttm (2): started_at, ended_at
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p48 <- read_csv("P1/202205.csv")
## Rows: 634858 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (7): ride_id, rideable_type, start_station_name, start_station_id, end_...
## dbl (4): start_lat, start_lng, end_lat, end_lng
## dttm (2): started_at, ended_at
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p49 <- read_csv("P1/202206.csv")
## Rows: 769204 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (7): ride_id, rideable_type, start_station_name, start_station_id, end_...
## dbl (4): start_lat, start_lng, end_lat, end_lng
## dttm (2): started_at, ended_at
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p50 <- read_csv("P1/202207.csv")
## Rows: 823488 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (7): ride_id, rideable_type, start_station_name, start_station_id, end_...
## dbl (4): start_lat, start_lng, end_lat, end_lng
## dttm (2): started_at, ended_at
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
Check Table
colnames(p10)
## [1] "trip_id" "start_time" "end_time"
## [4] "bikeid" "tripduration" "from_station_id"
## [7] "from_station_name" "to_station_id" "to_station_name"
## [10] "usertype" "gender" "birthyear"
colnames(p11)
## [1] "trip_id" "start_time" "end_time"
## [4] "bikeid" "tripduration" "from_station_id"
## [7] "from_station_name" "to_station_id" "to_station_name"
## [10] "usertype" "gender" "birthyear"
colnames(p12)
## [1] "trip_id" "start_time" "end_time"
## [4] "bikeid" "tripduration" "from_station_id"
## [7] "from_station_name" "to_station_id" "to_station_name"
## [10] "usertype" "gender" "birthyear"
colnames(p13)
## [1] "trip_id" "start_time" "end_time"
## [4] "bikeid" "tripduration" "from_station_id"
## [7] "from_station_name" "to_station_id" "to_station_name"
## [10] "usertype" "gender" "birthyear"
colnames(p14)
## [1] "01 - Rental Details Rental ID"
## [2] "01 - Rental Details Local Start Time"
## [3] "01 - Rental Details Local End Time"
## [4] "01 - Rental Details Bike ID"
## [5] "01 - Rental Details Duration In Seconds Uncapped"
## [6] "03 - Rental Start Station ID"
## [7] "03 - Rental Start Station Name"
## [8] "02 - Rental End Station ID"
## [9] "02 - Rental End Station Name"
## [10] "User Type"
## [11] "Member Gender"
## [12] "05 - Member Details Member Birthday Year"
colnames(p15)
## [1] "trip_id" "start_time" "end_time"
## [4] "bikeid" "tripduration" "from_station_id"
## [7] "from_station_name" "to_station_id" "to_station_name"
## [10] "usertype" "gender" "birthyear"
colnames(p16)
## [1] "trip_id" "start_time" "end_time"
## [4] "bikeid" "tripduration" "from_station_id"
## [7] "from_station_name" "to_station_id" "to_station_name"
## [10] "usertype" "gender" "birthyear"
colnames(p17)
## [1] "trip_id" "start_time" "end_time"
## [4] "bikeid" "tripduration" "from_station_id"
## [7] "from_station_name" "to_station_id" "to_station_name"
## [10] "usertype" "gender" "birthyear"
colnames(p18)
## [1] "trip_id" "start_time" "end_time"
## [4] "bikeid" "tripduration" "from_station_id"
## [7] "from_station_name" "to_station_id" "to_station_name"
## [10] "usertype" "gender" "birthyear"
colnames(p19)
## [1] "01 - Rental Details Rental ID"
## [2] "01 - Rental Details Local Start Time"
## [3] "01 - Rental Details Local End Time"
## [4] "01 - Rental Details Bike ID"
## [5] "01 - Rental Details Duration In Seconds Uncapped"
## [6] "03 - Rental Start Station ID"
## [7] "03 - Rental Start Station Name"
## [8] "02 - Rental End Station ID"
## [9] "02 - Rental End Station Name"
## [10] "User Type"
## [11] "Member Gender"
## [12] "05 - Member Details Member Birthday Year"
colnames(p20)
## [1] "trip_id" "start_time" "end_time"
## [4] "bikeid" "tripduration" "from_station_id"
## [7] "from_station_name" "to_station_id" "to_station_name"
## [10] "usertype" "gender" "birthyear"
colnames(p21)
## [1] "trip_id" "start_time" "end_time"
## [4] "bikeid" "tripduration" "from_station_id"
## [7] "from_station_name" "to_station_id" "to_station_name"
## [10] "usertype" "gender" "birthyear"
colnames(p22)
## [1] "ride_id" "rideable_type" "started_at"
## [4] "ended_at" "start_station_name" "start_station_id"
## [7] "end_station_name" "end_station_id" "start_lat"
## [10] "start_lng" "end_lat" "end_lng"
## [13] "member_casual"
colnames(p23)
## [1] "ride_id" "rideable_type" "started_at"
## [4] "ended_at" "start_station_name" "start_station_id"
## [7] "end_station_name" "end_station_id" "start_lat"
## [10] "start_lng" "end_lat" "end_lng"
## [13] "member_casual"
colnames(p24)
## [1] "ride_id" "rideable_type" "started_at"
## [4] "ended_at" "start_station_name" "start_station_id"
## [7] "end_station_name" "end_station_id" "start_lat"
## [10] "start_lng" "end_lat" "end_lng"
## [13] "member_casual"
colnames(p25)
## [1] "ride_id" "rideable_type" "started_at"
## [4] "ended_at" "start_station_name" "start_station_id"
## [7] "end_station_name" "end_station_id" "start_lat"
## [10] "start_lng" "end_lat" "end_lng"
## [13] "member_casual"
colnames(p26)
## [1] "ride_id" "rideable_type" "started_at"
## [4] "ended_at" "start_station_name" "start_station_id"
## [7] "end_station_name" "end_station_id" "start_lat"
## [10] "start_lng" "end_lat" "end_lng"
## [13] "member_casual"
colnames(p27)
## [1] "ride_id" "rideable_type" "started_at"
## [4] "ended_at" "start_station_name" "start_station_id"
## [7] "end_station_name" "end_station_id" "start_lat"
## [10] "start_lng" "end_lat" "end_lng"
## [13] "member_casual"
colnames(p28)
## [1] "ride_id" "rideable_type" "started_at"
## [4] "ended_at" "start_station_name" "start_station_id"
## [7] "end_station_name" "end_station_id" "start_lat"
## [10] "start_lng" "end_lat" "end_lng"
## [13] "member_casual"
colnames(p29)
## [1] "ride_id" "rideable_type" "started_at"
## [4] "ended_at" "start_station_name" "start_station_id"
## [7] "end_station_name" "end_station_id" "start_lat"
## [10] "start_lng" "end_lat" "end_lng"
## [13] "member_casual"
colnames(p30)
## [1] "ride_id" "rideable_type" "started_at"
## [4] "ended_at" "start_station_name" "start_station_id"
## [7] "end_station_name" "end_station_id" "start_lat"
## [10] "start_lng" "end_lat" "end_lng"
## [13] "member_casual"
colnames(p31)
## [1] "ride_id" "rideable_type" "started_at"
## [4] "ended_at" "start_station_name" "start_station_id"
## [7] "end_station_name" "end_station_id" "start_lat"
## [10] "start_lng" "end_lat" "end_lng"
## [13] "member_casual"
colnames(p32)
## [1] "ride_id" "rideable_type" "started_at"
## [4] "ended_at" "start_station_name" "start_station_id"
## [7] "end_station_name" "end_station_id" "start_lat"
## [10] "start_lng" "end_lat" "end_lng"
## [13] "member_casual"
colnames(p33)
## [1] "ride_id" "rideable_type" "started_at"
## [4] "ended_at" "start_station_name" "start_station_id"
## [7] "end_station_name" "end_station_id" "start_lat"
## [10] "start_lng" "end_lat" "end_lng"
## [13] "member_casual"
colnames(p34)
## [1] "ride_id" "rideable_type" "started_at"
## [4] "ended_at" "start_station_name" "start_station_id"
## [7] "end_station_name" "end_station_id" "start_lat"
## [10] "start_lng" "end_lat" "end_lng"
## [13] "member_casual"
colnames(p35)
## [1] "ride_id" "rideable_type" "started_at"
## [4] "ended_at" "start_station_name" "start_station_id"
## [7] "end_station_name" "end_station_id" "start_lat"
## [10] "start_lng" "end_lat" "end_lng"
## [13] "member_casual"
colnames(p36)
## [1] "ride_id" "rideable_type" "started_at"
## [4] "ended_at" "start_station_name" "start_station_id"
## [7] "end_station_name" "end_station_id" "start_lat"
## [10] "start_lng" "end_lat" "end_lng"
## [13] "member_casual"
colnames(p37)
## [1] "ride_id" "rideable_type" "started_at"
## [4] "ended_at" "start_station_name" "start_station_id"
## [7] "end_station_name" "end_station_id" "start_lat"
## [10] "start_lng" "end_lat" "end_lng"
## [13] "member_casual"
colnames(p38)
## [1] "ride_id" "rideable_type" "started_at"
## [4] "ended_at" "start_station_name" "start_station_id"
## [7] "end_station_name" "end_station_id" "start_lat"
## [10] "start_lng" "end_lat" "end_lng"
## [13] "member_casual"
colnames(p39)
## [1] "ride_id" "rideable_type" "started_at"
## [4] "ended_at" "start_station_name" "start_station_id"
## [7] "end_station_name" "end_station_id" "start_lat"
## [10] "start_lng" "end_lat" "end_lng"
## [13] "member_casual"
colnames(p40)
## [1] "ride_id" "rideable_type" "started_at"
## [4] "ended_at" "start_station_name" "start_station_id"
## [7] "end_station_name" "end_station_id" "start_lat"
## [10] "start_lng" "end_lat" "end_lng"
## [13] "member_casual"
colnames(p41)
## [1] "ride_id" "rideable_type" "started_at"
## [4] "ended_at" "start_station_name" "start_station_id"
## [7] "end_station_name" "end_station_id" "start_lat"
## [10] "start_lng" "end_lat" "end_lng"
## [13] "member_casual"
colnames(p42)
## [1] "ride_id" "rideable_type" "started_at"
## [4] "ended_at" "start_station_name" "start_station_id"
## [7] "end_station_name" "end_station_id" "start_lat"
## [10] "start_lng" "end_lat" "end_lng"
## [13] "member_casual"
colnames(p43)
## [1] "ride_id" "rideable_type" "started_at"
## [4] "ended_at" "start_station_name" "start_station_id"
## [7] "end_station_name" "end_station_id" "start_lat"
## [10] "start_lng" "end_lat" "end_lng"
## [13] "member_casual"
colnames(p44)
## [1] "ride_id" "rideable_type" "started_at"
## [4] "ended_at" "start_station_name" "start_station_id"
## [7] "end_station_name" "end_station_id" "start_lat"
## [10] "start_lng" "end_lat" "end_lng"
## [13] "member_casual"
colnames(p45)
## [1] "ride_id" "rideable_type" "started_at"
## [4] "ended_at" "start_station_name" "start_station_id"
## [7] "end_station_name" "end_station_id" "start_lat"
## [10] "start_lng" "end_lat" "end_lng"
## [13] "member_casual"
colnames(p46)
## [1] "ride_id" "rideable_type" "started_at"
## [4] "ended_at" "start_station_name" "start_station_id"
## [7] "end_station_name" "end_station_id" "start_lat"
## [10] "start_lng" "end_lat" "end_lng"
## [13] "member_casual"
colnames(p47)
## [1] "ride_id" "rideable_type" "started_at"
## [4] "ended_at" "start_station_name" "start_station_id"
## [7] "end_station_name" "end_station_id" "start_lat"
## [10] "start_lng" "end_lat" "end_lng"
## [13] "member_casual"
colnames(p48)
## [1] "ride_id" "rideable_type" "started_at"
## [4] "ended_at" "start_station_name" "start_station_id"
## [7] "end_station_name" "end_station_id" "start_lat"
## [10] "start_lng" "end_lat" "end_lng"
## [13] "member_casual"
colnames(p49)
## [1] "ride_id" "rideable_type" "started_at"
## [4] "ended_at" "start_station_name" "start_station_id"
## [7] "end_station_name" "end_station_id" "start_lat"
## [10] "start_lng" "end_lat" "end_lng"
## [13] "member_casual"
colnames(p50)
## [1] "ride_id" "rideable_type" "started_at"
## [4] "ended_at" "start_station_name" "start_station_id"
## [7] "end_station_name" "end_station_id" "start_lat"
## [10] "start_lng" "end_lat" "end_lng"
## [13] "member_casual"
Note That P14 and P19 have different table, specifically for rental bike.
p14_desc <- p14 %>%
rename(time= "01 - Rental Details Local Start Time") %>%
arrange(desc(time))
p14_desc
p14
We have different format of databases which is:
Group 1 = p14, p19 ;;; For Rental Bike, which also include member and casual Group 2 = p1 to p13 & p15 to p19 and p20 to p21 Group 3 = p22 to p50
However, these three type collected to same rawdata, however, they just use different column name; therefore trying to combine all together.
colnames(p14)
## [1] "01 - Rental Details Rental ID"
## [2] "01 - Rental Details Local Start Time"
## [3] "01 - Rental Details Local End Time"
## [4] "01 - Rental Details Bike ID"
## [5] "01 - Rental Details Duration In Seconds Uncapped"
## [6] "03 - Rental Start Station ID"
## [7] "03 - Rental Start Station Name"
## [8] "02 - Rental End Station ID"
## [9] "02 - Rental End Station Name"
## [10] "User Type"
## [11] "Member Gender"
## [12] "05 - Member Details Member Birthday Year"
colnames(p11)
## [1] "trip_id" "start_time" "end_time"
## [4] "bikeid" "tripduration" "from_station_id"
## [7] "from_station_name" "to_station_id" "to_station_name"
## [10] "usertype" "gender" "birthyear"
colnames(p22)
## [1] "ride_id" "rideable_type" "started_at"
## [4] "ended_at" "start_station_name" "start_station_id"
## [7] "end_station_name" "end_station_id" "start_lat"
## [10] "start_lng" "end_lat" "end_lng"
## [13] "member_casual"
Investigate each column before finalize Name for Station seem to be inconsistency so we use ID to identify Stations. rideable_type is always docked bike
###New table’s column will consist of: ride_id = trip_id = “01 - Rental Details Rental ID” started_at = starttime = “01 - Rental Details Local Start Time” ended_at = stoptime =“01 - Rental Details Local End Time” start_station_id = from_station_id = “03 - Rental Start Station ID” end_station_id = to_station_id = “02 - Rental End Station ID” member_casual = usertype = “User Type” rideable_type >>> “classic_bike” “electric_bike” “docked_bike”
###cutted column consist of: member gender birthyear lat and lng
###group group 1 = p14, p19 ;;; For Rental Bike, which also include member and casual group 2 = p1 to p13 & p15 to p19 and p20 to p21 group 3 = p22 to p50
####Union
g2020 <- union(union(
union(union(p22,p23),union(p24,p25)),
union(union(p26,p27),union(p28,p29))),p30)
#We found that end_station_id and start_station_id in g2020 is in double therefore; convert to char
g2020$end_station_id <- as.character(g2020$end_station_id)
g2020$start_station_id <- as.character(g2020$end_station_id)
g2020 <- union(g2020,p31)
g2021 <- union(union(union(p32,union(p33,p34)),union(union(p35,p36),union(p37,p38))),union(union(union(p39,p40),union(p41,p42)),p43))
g2022 <- union(union(p44,union(p45,p46)),union(union(p47,p48),union(p49,p50)))
#Final grouping for group3
g2020_to_g2022 <- union(union(g2020,g2021),g2022)
###GROUP1 - 2
##CONVERT
p14 <- read_csv("P1/201801_to_03.csv")
## Rows: 387145 Columns: 12
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (4): 03 - Rental Start Station Name, 02 - Rental End Station Name, User...
## dbl (5): 01 - Rental Details Rental ID, 01 - Rental Details Bike ID, 03 - R...
## dttm (2): 01 - Rental Details Local Start Time, 01 - Rental Details Local En...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p14 <- p14 %>%
rename(trip_id = "01 - Rental Details Rental ID" ) %>%
rename(start_time = "01 - Rental Details Local Start Time" ) %>%
rename(end_time = "01 - Rental Details Local End Time" ) %>%
rename(bikeid = "01 - Rental Details Bike ID") %>%
rename(tripduration = "01 - Rental Details Duration In Seconds Uncapped") %>%
rename(from_station_id = "03 - Rental Start Station ID" ) %>%
rename(from_station_name = "03 - Rental Start Station Name" ) %>%
rename(to_station_id = "02 - Rental End Station ID" ) %>%
rename(to_station_name = "02 - Rental End Station Name" ) %>%
rename(usertype = "User Type" ) %>%
rename(gender = "Member Gender" ) %>%
rename(birthyear = "05 - Member Details Member Birthday Year" )
p19 <- p19 <- read_csv("P1/201904_to_06.csv")
## Rows: 1108163 Columns: 12
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (4): 03 - Rental Start Station Name, 02 - Rental End Station Name, User...
## dbl (5): 01 - Rental Details Rental ID, 01 - Rental Details Bike ID, 03 - R...
## dttm (2): 01 - Rental Details Local Start Time, 01 - Rental Details Local En...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
p19 <- p19 %>%
rename(trip_id = "01 - Rental Details Rental ID" ) %>%
rename(start_time = "01 - Rental Details Local Start Time" ) %>%
rename(end_time = "01 - Rental Details Local End Time" ) %>%
rename(bikeid = "01 - Rental Details Bike ID") %>%
rename(tripduration = "01 - Rental Details Duration In Seconds Uncapped") %>%
rename(from_station_id = "03 - Rental Start Station ID" ) %>%
rename(from_station_name = "03 - Rental Start Station Name" ) %>%
rename(to_station_id = "02 - Rental End Station ID" ) %>%
rename(to_station_name = "02 - Rental End Station Name" ) %>%
rename(usertype = "User Type" ) %>%
rename(gender = "Member Gender" ) %>%
rename(birthyear = "05 - Member Details Member Birthday Year" )
# start_time and end_time in g2017 is in char format therefore; convert into dttm format
#first we test the syntax.
dates <- p10 %>%
select(start_time,end_time)
dates$start_time <- strptime(dates$start_time, format="%m/%d/%Y%H:%M:%S") #THIS DATE FORMAT (format=) TELL WHAT FORMAT WE HAVE BEFORE CONVERT INTO STANDARD FORMAT YY-MM-DD H:M:S
g2017 <- union(union(p10,p11), union(p12,p13))
g2017$start_time <- strptime(g2017$start_time, format="%m/%d/%Y%H:%M:%S")
g2017$end_time <- strptime(g2017$end_time, format="%m/%d/%Y%H:%M:%S")
g2018 <- union(union(p14,p15), union(p16,p17))
g2019 <- union(union(p18,p19), union(p20,p21))
g2017_to_g2019 <- union(union(g2017,g2018),g2019)
#Reorder before union
## removed tripduration (will calculate later)
## removed bikeid, since we will don't need this.
g1 <- g2017_to_g2019 %>%
add_column(rideable_type = "one_type") %>%
select(trip_id,start_time,end_time,from_station_id,from_station_name,to_station_id,to_station_name,usertype,rideable_type)
g2 <- g2020_to_g2022 %>%
select(ride_id,started_at,ended_at,start_station_id,start_station_name,end_station_id,end_station_name,member_casual,rideable_type)
# Convert g1 format before union
g1$trip_id <- as.character(g1$trip_id)
g1$from_station_id <- as.character(g1$from_station_id)
g1$to_station_id <- as.character(g1$to_station_id)
#Rename g2017_to_g2019 to the same format as g2020_to_g2022 before union
g1 <- g1 %>%
rename(ride_id = trip_id ) %>%
rename(started_at = start_time ) %>%
rename(ended_at = end_time ) %>%
rename(start_station_id = from_station_id ) %>%
rename(start_station_name = from_station_name ) %>%
rename(end_station_id = to_station_id ) %>%
rename(end_station_name = to_station_name ) %>%
rename(member_casual = usertype )
#now we union g2017_to_g2019 together with g2020_to_g2022
the_data <- union(g1,g2)
head(the_data)
working with the_data
the_data <- the_data %>%
mutate(duration = ended_at - started_at)
the_data %>%
drop_na() %>%
arrange(duration)
###Some ended_at value has higher value than started_at which is impossible, meaning there is some error in data collection processes ####Trying to drop 12,044 row of 23,489,045 which will have little effect to our data, however, further investigate of this incorrect data point have to be conduct.
the_data <- the_data %>%
filter(ended_at >= started_at)
###Some duration equal to 1,181, this might because of the cancel of service, which considering small number to 22 millions, try droping
the_data %>%
filter(duration != 0) %>%
arrange(duration)
###After drop the value we found that some little number of duration is the cause from HQ QR station, which is the usage of company personal itself, therefore, filter out start_station_id = 675 & end_station_id = 675, and filter out duration that have less value than 30(we use this number to classify it as false rent order, however further investigation have to be)
the_data <- the_data %>%
filter(start_station_id != 675 & the_data$end_station_id != 675) %>%
filter(duration > 30) %>%
arrange(-duration)
save(the_data,file="the_data.RData")
#load("the_data.RData"))